Retrospective cohort study.We obtained data for this study from the 'Cohort Hip and Cohort Knee' (CHECK) study. Participants who presented with knee osteoarthritis at baseline were included. We assessed baseline patient parameters such as demographics, anamnesis and physical examination measurements. Pain outcome measure was assessed annually using a numeric rating scale. Different pain trajectories were defined by latent class growth analysis. Multinomial logistic regression was used to calculate relative risk ratios.In total, 705 participants were included. Six distinct pain trajectories were identified with favourable and unfavourable courses. We found significant differences in baseline characteristics between the different pain trajectories, including BMI; symptom severity; and pain coping strategies. Higher BMI, lower education, presence of co-morbidities, higher activity limitation scores and joint space tenderness were more often associated with trajectories characterized by more pain at first presentation and pain progression. No association was found for baseline radiographic features.We defined six distinct pain trajectories in individuals with early symptomatic knee osteoarthritis. Our results can help physicians identify those patients that require more frequent monitoring compared patients for whom a watch-and-wait policy seems justifiable. In general practice, radiography does not provide added value to the follow-up of early symptomatic knee osteoarthritis patients.